HTML-Pruner-Phi-3.8B开源HTML修剪模型 - 优化RAG系统检索结果建模

首页

HTML Pruner Phi 3.8B

由 zstanjj 开发

用于HTML在RAG系统中比纯文本更适合建模检索结果的HTML修剪模型

大型语言模型

Transformers

英语开源协议:Apache-2.0 #HTML无损清理 #RAG系统优化 #块树修剪

下载量 319

发布时间 : 10/16/2024

模型简介

该模型专注于处理HTML格式的检索结果，通过无损HTML清理和基于块树的两步HTML修剪技术，优化RAG系统中的知识检索效率。

模型特点

无损HTML清理

仅删除完全不相关的内容并压缩冗余结构，保留原始HTML中的所有语义信息

基于块树的两步HTML修剪

第一步使用嵌入模型计算块的分数，第二步使用路径生成模型，实现高效HTML修剪

HTML格式优化

专门针对RAG系统优化HTML格式的检索结果，提高知识检索效率

模型能力

HTML文档清理

HTML内容修剪

语义信息保留

RAG系统优化

使用案例

信息检索

网页内容精简

从复杂HTML网页中提取关键信息，去除冗余内容

获得更简洁且保留语义的HTML内容

RAG系统知识格式化

为RAG系统准备HTML格式的外部知识源

提高RAG系统的检索效率和准确性

🚀 HTMLRAG模型

我们发布了用于RAG系统的HTML修剪器模型，该模型使用HTML而非纯文本处理检索结果，在信息处理上更具优势。

🚀 快速开始

本项目发布了用于 HtmlRAG: HTML is Better Than Plain Text for Modeling Retrieval Results in RAG Systems 的HTML修剪器模型。

有用的链接：📄 论文 • 🤗 Hugging Face • 💻 Github

我们提出了HtmlRAG，它在RAG系统中使用HTML而非纯文本作为外部知识的格式。为了处理HTML带来的长上下文问题，我们提出了 无损HTML清理 和 基于块树的两步HTML修剪 方法。

无损HTML清理：此清理过程仅移除完全不相关的内容并压缩冗余结构，保留原始HTML中的所有语义信息。无损HTML清理后的压缩HTML适用于具有长上下文大语言模型且在生成前不愿丢失任何信息的RAG系统。
基于块树的两步HTML修剪：基于块树的HTML修剪包括两个步骤，均在块树结构上进行。第一步修剪使用嵌入模型为块计算分数，第二步使用路径生成模型。第一步处理无损HTML清理的结果，第二步处理第一步修剪的结果。

🌟 如果你使用此模型，请给我们的 GitHub仓库 点个星支持我们。你的支持对我们意义重大！

✨ 主要特性

使用HTML作为RAG系统外部知识的格式，提升信息处理效果。
提出无损HTML清理和基于块树的两步HTML修剪方法，有效处理HTML长上下文问题。

📦 安装指南

使用pip安装包：

pip install htmlrag

或者从源代码安装包：

pip install -e .

💻 使用示例

基础用法

HTML清理

from htmlrag import clean_html

question = "When was the bellagio in las vegas built?"
html = """
<html>
<head>
<h1>Bellagio Hotel in Las</h1>
</head>
<body>
<p class="class0">The Bellagio is a luxury hotel and casino located on the Las Vegas Strip in Paradise, Nevada. It was built in 1998.</p>
</body>
<div>
<div>
<p>Some other text</p>
<p>Some other text</p>
</div>
</div>
<p class="class1"></p>
<!-- Some comment -->
<script type="text/javascript">
document.write("Hello World!");
</script>
</html>
"""

#. alternatively you can read html files and merge them
# html_files=["/path/to/html/file1.html", "/path/to/html/file2.html"]
# htmls=[open(file).read() for file in html_files]
# html = "\n".join(htmls)

simplified_html = clean_html(html)
print(simplified_html)

# <html>
# <h1>Bellagio Hotel in Las</h1>
# <p>The Bellagio is a luxury hotel and casino located on the Las Vegas Strip in Paradise, Nevada. It was built in 1998.</p>
# <div>
# <p>Some other text</p>
# <p>Some other text</p>
# </div>
# </html>

配置修剪参数

真实世界的HTML文档可能更长、更复杂，可配置以下参数：

# Maximum number of words in a node when constructing the block tree for pruning with the embedding model
MAX_NODE_WORDS_EMBED = 10 
# MAX_NODE_WORDS_EMBED = 256 # a recommended setting for real-world HTML documents
# Maximum number of tokens in the output HTML document pruned with the embedding model
MAX_CONTEXT_WINDOW_EMBED = 60
# MAX_CONTEXT_WINDOW_EMBED = 6144 # a recommended setting for real-world HTML documents
# Maximum number of words in a node when constructing the block tree for pruning with the generative model
MAX_NODE_WORDS_GEN = 5
# MAX_NODE_WORDS_GEN = 128 # a recommended setting for real-world HTML documents
# Maximum number of tokens in the output HTML document pruned with the generative model
MAX_CONTEXT_WINDOW_GEN = 32
# MAX_CONTEXT_WINDOW_GEN = 4096 # a recommended setting for real-world HTML documents

构建块树

from htmlrag import build_block_tree

block_tree, simplified_html = build_block_tree(simplified_html, max_node_words=MAX_NODE_WORDS_EMBED)
# block_tree, simplified_html = build_block_tree(simplified_html, max_node_words=MAX_NODE_WORDS_GEN, zh_char=True) # for Chinese text
for block in block_tree:
    print("Block Content: ", block[0])
    print("Block Path: ", block[1])
    print("Is Leaf: ", block[2])
    print("")

# Block Content:  <h1>Bellagio Hotel in Las</h1>
# Block Path:  ['html', 'title']
# Is Leaf:  True
# 
# Block Content:  <div>
# <p>Some other text</p>
# <p>Some other text</p>
# </div>
# Block Path:  ['html', 'div']
# Is Leaf:  True
# 
# Block Content:  <p>The Bellagio is a luxury hotel and casino located on the Las Vegas Strip in Paradise, Nevada. It was built in 1998.</p>
# Block Path:  ['html', 'p']
# Is Leaf:  True

使用嵌入模型修剪HTML块

from htmlrag import EmbedHTMLPruner

embed_model="BAAI/bge-large-en"
query_instruction_for_retrieval = "Instruct: Given a web search query, retrieve relevant passages that answer the query\nQuery: "
embed_html_pruner = EmbedHTMLPruner(embed_model=embed_model, local_inference=True, query_instruction_for_retrieval = query_instruction_for_retrieval)
# alternatively you can init a remote TEI model, refer to https://github.com/huggingface/text-embeddings-inference.
# tei_endpoint="http://YOUR_TEI_ENDPOINT"
# embed_html_pruner = EmbedHTMLPruner(embed_model=embed_model, local_inference=False, query_instruction_for_retrieval = query_instruction_for_retrieval, endpoint=tei_endpoint)
block_rankings=embed_html_pruner.calculate_block_rankings(question, simplified_html, block_tree)
print(block_rankings)

# [2, 0, 1]

#. alternatively you can use bm25 to rank the blocks
from htmlrag import BM25HTMLPruner
bm25_html_pruner = BM25HTMLPruner()
block_rankings = bm25_html_pruner.calculate_block_rankings(question, simplified_html, block_tree)
print(block_rankings)

# [2, 0, 1]

from transformers import AutoTokenizer

chat_tokenizer = AutoTokenizer.from_pretrained("meta-llama/Llama-3.1-70B-Instruct")

pruned_html = embed_html_pruner.prune_HTML(simplified_html, block_tree, block_rankings, chat_tokenizer, MAX_CONTEXT_WINDOW_EMBED)
print(pruned_html)

# <html>
# <h1>Bellagio Hotel in Las</h1>
# <p>The Bellagio is a luxury hotel and casino located on the Las Vegas Strip in Paradise, Nevada. It was built in 1998.</p>
# </html>

使用生成模型修剪HTML块

from htmlrag import GenHTMLPruner
import torch

# construct a finer block tree
block_tree, pruned_html = build_block_tree(pruned_html, max_node_words=MAX_NODE_WORDS_GEN)
# block_tree, pruned_html = build_block_tree(pruned_html, max_node_words=MAX_NODE_WORDS_GEN, zh_char=True) # for Chinese text
for block in block_tree:
    print("Block Content: ", block[0])
    print("Block Path: ", block[1])
    print("Is Leaf: ", block[2])
    print("")
    
# Block Content:  <h1>Bellagio Hotel in Las</h1>
# Block Path:  ['html', 'title']
# Is Leaf:  True
# 
# Block Content:  <p>The Bellagio is a luxury hotel and casino located on the Las Vegas Strip in Paradise, Nevada. It was built in 1998.</p>
# Block Path:  ['html', 'p']
# Is Leaf:  True

ckpt_path = "zstanjj/HTML-Pruner-Phi-3.8B"
if torch.cuda.is_available():
    device="cuda"
else:
    device="cpu"
gen_embed_pruner = GenHTMLPruner(gen_model=ckpt_path, device=device)
block_rankings = gen_embed_pruner.calculate_block_rankings(question, pruned_html, block_tree)
print(block_rankings)

# [1, 0]

pruned_html = gen_embed_pruner.prune_HTML(pruned_html, block_tree, block_rankings, chat_tokenizer, MAX_CONTEXT_WINDOW_GEN)
print(pruned_html)

# <p>The Bellagio is a luxury hotel and casino located on the Las Vegas Strip in Paradise, Nevada. It was built in 1998.</p>

📚 详细文档

模型结果

HTML-Pruner-Phi-3.8B 和 HTML-Pruner-Llama-1B 以Llama-3.1-70B-Instruct作为聊天模型的结果。

数据集	ASQA	HotpotQA	NQ	TriviaQA	MuSiQue	ELI5
指标	EM	EM	EM	EM	EM	ROUGE-L
BM25	49.50	38.25	47.00	88.00	9.50	16.15
BGE	68.00	41.75	59.50	93.00	12.50	16.20
E5-Mistral	63.00	36.75	59.50	90.75	11.00	16.17
LongLLMLingua	62.50	45.00	56.75	92.50	10.25	15.84
JinaAI Reader	55.25	34.25	48.25	90.00	9.25	16.06
HtmlRAG-Phi-3.8B	68.50	46.25	60.50	93.50	13.25	16.33
HtmlRAG-Llama-1B	66.50	45.00	60.75	93.00	10.00	16.25

📄 许可证

本项目采用Apache 2.0许可证。

📚 引用

@misc{tan2024htmlraghtmlbetterplain,
      title={HtmlRAG: HTML is Better Than Plain Text for Modeling Retrieved Knowledge in RAG Systems}, 
      author={Jiejun Tan and Zhicheng Dou and Wen Wang and Mang Wang and Weipeng Chen and Ji-Rong Wen},
      year={2024},
      eprint={2411.02959},
      archivePrefix={arXiv},
      primaryClass={cs.IR},
      url={https://arxiv.org/abs/2411.02959}, 
}